Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and counts associated with numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preceding words like "the", "a", "since"

    np_acts-logits-general · gemini-2.0-flash

    buyers premium, president, eastern environments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    μως
    -0.77
     but
    -0.75
     aber
    -0.72
     also
    -0.68
     plus
    -0.67
     obstante
    -0.65
     him
    -0.64
     moreover
    -0.64
    但我
    -0.64
    但他
    -0.64
    POSITIVE LOGITS
    Although
    0.99
    While
    0.97
    The
    0.97
    Since
    0.96
     Although
    0.93
     Since
    0.92
    There
    0.89
    Due
    0.89
    During
    0.88
    When
    0.88
    Act Density 0.545%

    No Known Activations